I built Airut as an experiment - could email be a good fit for talking to a coding agent? Turns out that the answer is yes, at least for me personally - I immediately moved almost all of my development to happen exclusively over email.

Email is perfect fit for async long-form conversation, naturally threaded, and with excellent UX across platforms. Each email thread becomes a Claude Code session within automatically created sandboxed workspace. Working on multiple things in parallel requires no additional thought - they just exist as independent email threads in your inbox. Friction to start a new task is what I would consider zero - just send an email (without having to worry about a human judging your poor grammar even!)

I recently added slack support as well, inspired by Spotify’s “Honk”. Slack having native threading maps to Airut’s model reasonably well. Although I wish Slack had better UX for switching between threads.

Airut works best when the project is set up for agentic development and the agent has necessary access to push code for review. I’ve tried to make this possible securely; Airut for example has “masked secrets” feature where the container running Claude Code doesn’t hold the real authentication tokens, only look-alike surrogates which are swapped to real ones on the way out by a proxy.

Project is open-source (MIT) and should be straightforward to set up on a Linux machine or VM. I’d love to hear feedback about the conceptual model and the sandboxing implementation.